Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean Embeddings

by   Jean-Francois Ton, et al.
University of Oxford

Current meta-learning approaches focus on learning functional representations of relationships between variables, i.e. on estimating conditional expectations in regression. In many applications, however, we are faced with conditional distributions which cannot be meaningfully summarized using expectation only (due to e.g. multimodality). Hence, we consider the problem of conditional density estimation in the meta-learning setting. We introduce a novel technique for meta-learning which combines neural representation and noise-contrastive estimation with the established literature of conditional mean embeddings into reproducing kernel Hilbert spaces. The method is validated on synthetic and real-world problems, demonstrating the utility of sharing learned representations across multiple conditional density estimation tasks.


page 7

page 8

page 13

page 14

page 15

page 18

page 21

page 22


MCD: Marginal Contrastive Discrimination for conditional density estimation

We consider the problem of conditional density estimation, which is a ma...

Kernel Conditional Density Operators

We introduce a conditional density estimation model termed the condition...

Task-similarity Aware Meta-learning through Nonparametric Kernel Regression

Meta-learning refers to the process of abstracting a learning rule for a...

Conditional expectation using compactification operators

The separate tasks of denoising, conditional expectation and manifold le...

Contrastive Conditional Neural Processes

Conditional Neural Processes (CNPs) bridge neural networks with probabil...

Kernel Regression by Mode Calculation of the Conditional Probability Distribution

The most direct way to express arbitrary dependencies in datasets is to ...

Better Conditional Density Estimation for Neural Networks

The vast majority of the neural network literature focuses on predicting...

Please sign up or login with your details

Forgot password? Click here to reset